Chinese content蚂蚁百灵开源 Ling-3.1-flash:总参数 560B,支持 1M 上下文
蚂蚁百灵把 560B 的 Ling-3.1-flash 开源了,激活只有 25B,量化后 4 张卡就能跑,还带 1M 上下文,自己部署的团队可以看看。
IT之家Source
蚂蚁百灵把 560B 的 Ling-3.1-flash 开源了,激活只有 25B,量化后 4 张卡就能跑,还带 1M 上下文,自己部署的团队可以看看。
蚂蚁又开源了一个大模型,560B 总参但每个 token 只跑 25B,还能塞 100 万 token 上下文,MIT 协议想怎么商用都行。
A sparse MoE that activates only ~25B of 560B parameters means self-hosters get trillion-class capacity at a fraction of the serving cost, now with day-0 vLLM compatibility. Teams building front-end or prototype generation pipelines can run it on their own GPUs instead of relying on API providers. It also signals Ant Group's push to compete with open-weight releases from DeepSeek and Qwen in the global open-source ecosystem.